dual cpu 64 core - page 4

New comment
 
Dominik Christian Egert #:
Hyper threading has always been working, it is just not recommended.

The wizard will not use these cores, you need to do it manually.

Understood!!..

Could you share some disadvantages of using HT?

It's not going to affect my servers?

Thanks.. 

 
Hyper threading is basically sharing the input pipeline of a CPU core to two tasks. It was originally designed to fill the CPUs pipeline.

A core shared by HT will not be like 2* a separate core, it will introduce some penalty to the performance and might average around something like 1.75 times a cores performance. Depending on the workload that's applied.

There can be cases where you get even almost full 2 times the performance, but as said, it depends on the workload.

Cache misses, memory usage, type of operations performed, to name a few..

Since the workload by an optimization run is quite alike for each thread, the penalty will be more severe, although, it might reduce load on the cache, since the processed Datastream is mostly the same.

But, this is only a brief scratch on the surface of what's going on behind the scenes.
 
Dominik Christian Egert #:
Hyper threading is basically sharing the input pipeline of a CPU core to two tasks. It was originally designed to fill the CPUs pipeline.

A core shared by HT will not be like 2* a separate core, it will introduce some penalty to the performance and might average around something like 1.75 times a cores performance. Depending on the workload that's applied.

There can be cases where you get even almost full 2 times the performance, but as said, it depends on the workload.

Cache misses, memory usage, type of operations performed, to name a few..

Since the workload by an optimization run is quite alike for each thread, the penalty will be more severe, although, it might reduce load on the cache, since the processed Datastream is mostly the same.

But, this is only a brief scratch on the surface of what's going on behind the scenes.

Cleared.. 

Thanks. :D

 

Hi guys, 
Have read through the recent posts and thought I would have had it sorted, however still unable to enable the missing 16 cores/threads.
I can see they are in the group 1 I'm assuming. However still unable to get metatester to see all the cores. If I enable the group 0, 1 or 2 it automatically disables group that was active prior.
(running 2x8360y processors)
Thanking anyone in advance for their help!


 
Don't set up affinity, let the OS handle it for you.

See if that works as expected. BTW, your utilization already looks good.

Remember, you need some resources for the OS, having all allocated to the tester will render your system unusable.
1234
New comment
Reason: